Corpus ID: 231942580

DeepWalking Backwards: From Embeddings Back to Graphs

@article{Chanpuriya2021DeepWalkingBF,
  title={DeepWalking Backwards: From Embeddings Back to Graphs},
  author={Sudhanshu Chanpuriya and Cameron Musco and Konstantinos Sotiropoulos and Charalampos E. Tsourakakis},
  journal={ArXiv},
  year={2021},
  volume={abs/2102.08532}
}
Low-dimensional node embeddings play a key role in analyzing graph datasets. However, little work studies exactly what information is encoded by popular embedding methods, and how this information correlates with performance in downstream learning tasks. We tackle this question by studying whether embeddings can be inverted to (approximately) recover the graph used to generate them. Focusing on a variant of the popular DeepWalk method [Perozzi et al., 2014, Qiu et al., 2018], we present… Expand

References

SHOWING 1-10 OF 27 REFERENCES
InfiniteWalk: Deep Network Embeddings as Laplacian Embeddings with a Nonlinearity
  • 4
  • PDF
Deep Neural Networks for Learning Graph Representations
  • 484
Node Embeddings and Exact Low-Rank Representations of Complex Networks
  • 1
  • Highly Influential
  • PDF
Structural Deep Network Embedding
  • 1,290
  • PDF
Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec
  • 364
  • Highly Influential
  • PDF
LINE: Large-scale Information Network Embedding
  • 2,658
  • PDF
node2vec: Scalable Feature Learning for Networks
  • 4,064
  • Highly Influential
  • PDF
DeepWalk: online learning of social representations
  • 4,111
  • Highly Influential
  • PDF
The impossibility of low-rank representations for triangle-rich complex networks
  • 11
  • PDF
...
1
2
3
...